Autors: Pandelova, A. L., Georgiev, I. N., Stoyanov, N. S., Dzhudzhev, B. P.
Title: Calibration of IoT-based System for Indoor Air Quality Monitoring
Keywords: calibration model, MQ-9, NOVA SDS011, air pollution, IoT

Abstract: The calibration of low-cost sensors is crucial for ensuring their accuracy and reliability. Calibration models introduce corrections to sensor readings by comparing them with reference data obtained from reference measuring instrument. This study examines two primary calibration approaches for an Internet of Things (IoT) sensor node equipped with an MQ-9 carbon monoxide sensor and a Nova SDS011 particulate matter sensor: algorithmic calibration based on manufacturer specifications, and on-field calibration (comprising single-point and multivariate linear regression approaches). The calibration models are evaluated using the coefficient of determination (R2), the sum of squared errors (SSE), and the mean absolute error (MAE). The results indicate that all three models are applicable for the MQ-9 sensor depending on the required precision, the obtained values are R2 = 0.7 (algorithmic), R2 = 0.67 (single-point), R2 = 0.93 (multivariate linear regression). In Nova SDS011, mandatory calib

References

    Issue

    2026 International Conference Automatics, Robotics and Artificial Intelligence (ICARAI), 2026, Bulgaria, DOI 10.1109/ICARAI70085.2026.11635113

    Copyright IEEE

    Full text of the publication

    Вид: пленарен доклад в национален форум с межд. уч., публикация в реферирано издание, индексирана в Scopus